[1]王拥军,马维华.一种基于 CSI 相位差的手势识别方法[J].计算机技术与发展,2020,30(04):14-19.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 003]
　WANG Yong-jun,MA Wei-hua.A Gesture Recognition Method Based on CSI Phase Difference[J].,2020,30(04):14-19.[doi:10. 3969 / j. issn. 1673-629X. 2020. 04. 003]
点击复制

一种基于 CSI 相位差的手势识别方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年04期
页码:
14-19
栏目:
智能、算法、系统工程
出版日期:
2020-04-10

文章信息/Info

Title:
A Gesture Recognition Method Based on CSI Phase Difference
文章编号:
1673-629X(2020)04-0014-06
作者:
王拥军; 马维华
南京航空航天大学 计算机科学与技术学院,江苏 南京 211106
Author(s):
WANG Yong-jun; MA Wei-hua
School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
与位置无关; 信道状态信息; 手势识别; 相位差; 动态时间规整
Keywords:
position-independent; channel state information; gesture recognition; phase difference; DTW
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 04. 003
摘要:
随着人机交互( HCI) 技术的发展,人体行为的感知和分析成为实现更高层次人机交互的重要一环,尤其是实现与位置无关的手势识别。 针对目前基于信道状态信息( channel state information,CSI) 的手势识别方法局限于中心链路的问题,提出基于 CSI 相位差的手势识别方法,充分利用多径效应和空间多样性,识别中心链路和非中心链路上的微弱手势信号。 由于 CSI 相位受时钟不同步和硬件缺陷的影响无法反映环境的变化,采用线性变换算法对其进行校准,并借助 MIMO(multiple-input multiple-output) 技术获得相位差。 在此基础上,利用 Hampel 滤波器和 Savitzky-Golay 滤波器滤除异常点和环境噪声。 由于频率多样性,根据平均绝对偏差( MAD) 选择变化最大的子载波,之后利用动态时间规整( DTW) 算法对手势进行分类。 实验结果表明,该方法能有效识别中心链路和非中心链路上的微弱手势信号,实现了与位置无关的识别;在中心链路和非中心链路上分别以 90% 和 86. 5% 的准确率识别 6 种手势,所需样本量小,识别时间短。
Abstract:
With the development of human-computer interaction (HCI) technology,the perception and analysis of human behavior has become an important part of achieving higher-level human-computer interaction, especially the realization of position-independent gesture recognition. Aiming at the problem that the current gesture recognition method based on channel state information (CSI) is limited to the central link,we propose a gesture recognition method based on CSI phase difference,which makes full use of multipath effects and spatial diversity to identify the weak gesture signal on a central link and non-central link. Since the raw CSI phase cannot reflect the environment change due to the clock is out-of-synchronization and hardware defects,it is calibrated by a linear transform algorithm and the phase difference is obtained by means of MIMO technique. Based on this,the Hampel filter and the Savitzky-Golay filter are used to filter out abnormal points and environmental noise. Due to the frequency diversity,the subcarrier that has maximum change is selected according to the mean absolute deviation (MAD) ,and then the gestures are classified by the dynamic time warping (DTW) algorithm. The experiment shows that the proposed method can effectively identify weak gesture signals on the central link and non-central link,and achieve position-independent recognition. It can recognize six gestures with 90% and 86. 5% accuracy on the central link and non-central link respectively,with small required sample size and short recognition time.

相似文献/References:

[1]李耀辉,苏元茂. 一种基于直视路径识别的无线接入点定位方法[J].计算机技术与发展,2018,28(02):112.[doi:10．3969/j．issn．1673－629X．2018．02．025]
　LI Yao-hui,SU Yuan-mao.An Access Point Positioning Method Based on Line-of-sight Identification[J].,2018,28(04):112.[doi:10．3969/j．issn．1673－629X．2018．02．025]
[2]吴春香,张建明.无线感知网络中动作识别的滤波算法[J].计算机技术与发展,2018,28(05):86.[doi:10.3969/j.issn.1673－629X.2018.05.020]
　WU Chun-xiang,ZHANG Jian-ming.Filtering Algorithm for Motion Ｒecognition in Wireless Sensor Networks[J].,2018,28(04):86.[doi:10.3969/j.issn.1673－629X.2018.05.020]
[3]丁文超,张俊宝,阴庚雷.基于 CRNN 的 CSI 动作识别[J].计算机技术与发展,2021,31(06):7.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 002]
　DING Wen-chao,ZHANG Jun-bao,YIN Geng-lei.CSI Action Recognition Based on CRNN[J].,2021,31(04):7.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 002]
[4]刘 伟,程春玲,杜金楷,等.一种基于改进深度卷积模型的室内定位方法[J].计算机技术与发展,2022,32(08):155.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 025]
　LIU Wei,CHENG Chun-ling,DU Jin-kai,et al.An Indoor Positioning Method Based on Improved Deep Convolution Mode[J].,2022,32(04):155.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 025]
[5]马永连*,张登银.基于域自适应网络的跨场景摔倒检测算法研究[J].计算机技术与发展,2023,33(10):86.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 014]
　MA Yong-lian*,ZHANG Deng-yin.Cross-scene Fall Detection Algorithm Based on Domain Adaptive Network[J].,2023,33(04):86.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 014]

更新日期/Last Update: 2020-04-10